Join Our Mission

Join the team
securing AI's future

We're building the world's most trusted AI security platform. Join our founding team and help shape the future of AI safety.

Founding Team Opportunity
Remote-First Culture
Equity & Growth

Why Join Garak?

Be part of a mission-driven team building the security infrastructure for the AI-powered future.

Mission-Critical Impact

Your work directly protects AI systems used by millions of people worldwide.

Founding Team Equity

Significant equity stake and the opportunity to shape company culture from day one.

Remote-First

Work from anywhere with flexible hours and a focus on results, not location.

Open Positions

Join our founding team and help build the future of AI security.

Security Research Engineer (Founding)
Remote / SF Bay Area
Security
Full-Time

About the role

As one of our first Security Research Engineers, you'll partner closely with the CTO to define and ship the core red-teaming and vulnerability-detection capabilities in Garak Enterprise. You'll own threat modeling, adversarial probe design, and hands-on validation against real LLMs—building the tools and methodology that our customers rely on to secure their AI agents.

What you will do

  • Design, implement, and harden a library of automated "attacks" (prompt-injection, jailbreak, jailbreak chaining, context poisoning, etc.)
  • Build novel metrics and detectors for LLM misbehavior (hallucination scoring, divergence detection, chain-of-thought exploits)
  • Translate academic research into production probes: prototype in Python, then harden for scale
  • Lead adversarial evaluations against OpenAI, Anthropic, Mistral, other LLMs in both cloud and on-prem contexts
  • Publish findings, benchmark reports, and whitepapers to establish Garak as the industry-standard security authority

You're a great fit if you have

  • 3+ years in security research, red-teaming, or adversarial ML (LLM focus highly preferred)
  • Strong Python skills, with production-quality code and test-driven development
  • Deep familiarity with prompt-based attacks, model vulnerabilities, or content-safety research
  • Experience writing reproducible benchmarks and statistical analysis of model outputs
  • Excellent written and verbal communication—able to distill complex attacks into actionable guidance

Nice to have

  • Prior open-source contributions in NLP, adversarial ML, or security tooling
  • Hands-on experience with LangChain, LlamaIndex, or comparable LLM-driving frameworks
  • Background in compliance frameworks (NIST, ISO 27001, EU AI Act) and security certification
Senior Backend/Platform Engineer (Founding)
Remote / SF Bay Area
Infrastructure
Full-Time

About the role

You'll architect and own the cloud-native infrastructure that runs Garak's red-teaming and monitoring platform at scale. From spinning up Kubernetes clusters to orchestrating secure, multi-tenant inference pipelines, you'll ensure our service is rock-solid, observable, and easy for customers to integrate into their CI/CD workflows.

What you will do

  • Design, build, and operate our production environment (AWS, EKS, managed and self-hosted)
  • Implement Infrastructure as Code (Terraform) to manage networks, IAM, databases, and auto-scaling services
  • Harden security posture: secure networking, secrets management, vulnerability scanning, and compliance controls
  • Build CI/CD pipelines (GitHub Actions or GitLab CI), integrate automated testing, and streamline release workflows
  • Set up logging, metrics, and alerting (Prometheus, Grafana, Datadog or similar) for SLO-driven operations
  • Mentor cross-functional teams on best practices for deployment, rollback, and disaster recovery

You're a great fit if you have

  • 5+ years in Backend/Platform or SRE roles, ideally in SaaS/ML environments
  • Deep experience with Kubernetes, Helm charts, and container networking in production
  • Proven track record on AWS (VPCs, EKS, RDS, SQS, IAM) and Infrastructure as Code (Terraform)
  • Strong scripting skills (Bash, Python, or Go) and automation mindset
  • End-to-end ownership of uptime, performance tuning, and incident response

Nice to have

  • Experience with multi-cloud or hybrid on-prem + cloud deployments
  • Background in SecOps: CI security, vulnerability management, SOC 2/ISO 27001 compliance
  • Familiarity with GPU-based inference, Redis/ElastiCache, or high-throughput message queues
Ready to Join Us?

Ready to Join Us?

Don't see a perfect fit? We're always looking for exceptional talent. Send us your resume and tell us how you'd like to contribute to AI security.